The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Despite its age, JPEG (formally, Rec. ITU-T T.81 — ISO/IEC 10918-1) is still the omnipresent image file format for lossy compression of photographic images. While its rate-distortion performance is not competitive with state-of-the-art schemes like JPEG 2000 or HEVC, manifold techniques have been developed over the years to improve its compression performance. This article provides a short review...
In this paper, we extend the nearest convex hull classifier to Symmetric Positive Definite (SPD) manifolds. SPD manifold features have been shown to have excellent performance in various image/video classification tasks. Unfortunately, SPD manifolds naturally possess non-Euclidean geometry, so existing Euclidean machineries such as the nearest convex hull classifier cannot be used directly. To that...
In this work, a novel and fast algorithm for real-time 3D body reconstruction from stereo sequences is proposed. The main contributions of this work consist of a novel approach for a statistically guided stereo processing and a data parallel iteration scheme for 3D estimation that includes temporal predecessors from a local spatial neighborhood. A purely GPU based implementation is provided that exhibits...
Hierarchical classification is a computational efficient approach for large-scale image classification. The main challenging issue of this approach is to deal with error propagation. Irrelevant branching decision made at a parent node cannot be corrected at its child nodes in traversing the tree for classification. This paper presents a novel approach to reduce branching error at a node by taking...
The directional intra prediction (DIP) modes in HEVC are capable of predicting local continuous image features. Recently, intra block copy (IBC) is proposed for screen content coding, aiming at predicting non-local recurrent image features. For natural video, we observe that recurrent features are often irregular and not aligned with blocks. Thus, we propose a combination of DIP and IBC with block...
This paper presents a novel algorithm that aims at minimizing the required decoding energy by exploiting a general energy model for HEVC-decoder solutions. We incorporate the energy model into the HEVC encoder such that it is capable of constructing a bit stream whose decoding process consumes less energy than the decoding process of a conventional bit stream. To achieve this, we propose to extend...
This paper presents efficient SIMD optimizations for the open-source Kvazaar HEVC intra encoder. The C implementation of Kvazaar is accelerated by Intel AVX2 instructions whose effect on Kvazaar ultrafast preset is profiled. According to our profiling results, C functions of SATD, DCT, quantization, and intra prediction account for over 60% of the total intra coding time of Kvazaar ultrafast preset...
We present a method of image sequence interpolation, which can generate a sequence of continuous intermediate frames between two input images. This method is based on a path framework that describes the motion information in the images. A path which starts from one input image, and ends at another input image is constructed for each pixel in the images. The main contribution of this paper is that...
Sparsity constrained single image super-resolution has been of much recent interest. A typical approach involves sparsely representing patches in a low-resolution (LR) input image via a dictionary of example LR patches, and then use the coefficients of this representation to generate the high-resolution (HR) output via an analogous HR dictionary. However, most existing sparse representation methods...
Estimation of salient regions in an input video is an active area of research due to its wide applications. In this paper, we propose a novel algorithm to estimate the eye gaze movement in a video using motion, color and structural cues with minimum outliers. The algorithm is generalized to capture salient information for the videos taken under different camera motions. The entire algorithm is parallelizable...
This paper introduces a segmentation approach, where a discriminative dictionary with objects' shape information is learned, followed by a sparse representation based segmentation process. In contrast with state-of-the-art sparse representation classification methods using discriminative dictionary learning, the proposed method learns a discriminative dictionary containing both intensity and shape...
Most of the existing works on person re-identification have focused on improving matching rate at top ranks. Few efforts are devoted to address the problem of efficient storage and fast search for person re-identification. In this paper, we investigate the prevailing hashing method, originally designed for large scale image retrieval, for fast person re-identification with efficient storage. We propose...
Fixed camera videos are obtained/used by surveillance, teleconference, remote lecturing. Since it is one of the most fundamental camera movement techniques, it is also frequently used in studio shots, drama/movie scenes. In this paper, simple and efficient coding method for such fixed camera videos is proposed. The proposal significantly improves the coding efficiency and generated bitstream is fully...
The latest high efficiency video coding (HEVC) standard achieves about 50% bit-rate reduction at equivalent visual quality compared to H.264/AVC. Sample adaptive offset (SAO) is one of the newly adopted tools right after deblocking filter, which can improve both coding efficiency and visual quality. However, for real-time encoding scenarios, the complexity of SAO is usually too high to be enabled...
Depth profile reconstruction of a scene at low light levels using an active imaging setup has wide-ranging applications in remote sensing. In such low-light imaging scenarios, single-photon detectors are employed to time-resolve individual photon detections. However, even with single-photon detectors, current frameworks are limited to using hundreds of photon detections at each pixel to mitigate Poisson...
Convolutional Neural Networks (CNNs) have delivered impressive state-of-the-art performances for many vision tasks, while the computation costs of these networks during test-time are notorious. Empirical results have discovered that CNNs have learned the redundant representations both within and across different layers. When CNNs are applied for binary classification, we investigate a method to exploit...
Motion estimation across low-resolütion frames and the reconstruction of high-resolütion images are two coupled sübproblems of multi-frame super-resolütion. This paper introduces a new joint optimization approach for motion estimation and image reconstrüction to address this interdependence. Our method is formulated via non-linear least squares optimization and combines two principles of robust süper-resolütion...
The main challenge in multi-view camera calibration is precise pose estimation of cameras, especially when their fields of view have very little overlap. This work proposes a very accurate multi-view camera calibration method that does not require cameras to share theirs fields of view. A rotating stage is used to move the calibration target along a known trajectory, consisting of pure rotation, through...
This paper presents a novel approach for the optimization of calibration parameters in structured light system (SLS). Different with conventional calibration algorithms, the proposed optimization algorithm is implemented in 3D space instead of 2D image space. The object used for parameter optimization can be a simple plane with some markers. A global optimal function is constructed to contain all...
Despite significant progress in pedestrian detection has been made in recent years, detecting pedestrians in crowded scenes remains a challenging problem. In this paper, we propose to use visual contexts based on scale and occlusion cues from detections at proximity to better detect pedestrians for surveillance applications. Specifically, we first apply detectors based on full body and parts to generate...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.